b11518
Mirrored from llama.cpp releases for archival readability. Support the source by reading on the original site.
metal: add the 128/96 flash attention kernels, accept every compiled …
Mirrored from llama.cpp releases for archival readability. Support the source by reading on the original site.
metal: add the 128/96 flash attention kernels, accept every compiled …
Discussion (0)
Sign in to join the discussion. Free account, 30 seconds — email code or GitHub.
Sign in →No comments yet. Sign in and be the first to say something.